© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12092
    Prev
    Next
    INDEX
    Explanations

    references to deeds or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "de" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    allery
    -0.72
     Flavoring
    -0.72
    Reviewer
    -0.68
     tremend
    -0.66
    hetti
    -0.65
     Atmosp
    -0.65
     Orbit
    -0.64
    ieri
    -0.62
    NetMessage
    -0.62
    POSITIVE LOGITS
    ploy
    1.30
    legate
    1.27
    utsche
    1.20
    legates
    1.19
    leted
    1.13
    cember
    1.02
    cker
    0.98
    bris
    0.97
    vel
    0.94
    vers
    0.92
    Activations Density 0.009%

    No Known Activations